Decorrelation-Based Feature Discovery: Diabetes
Jose Tamez
2023-09-29
- 1 Effect of UPSTM-Based Decorrelation
on Feature Discovery
- 1.0.1 Loading the libraries
- 1.1 Material and Methods
- 1.2 The Data
- 1.3 Generaring the report
- 1.4 The heatmap of the data
- 1.5 The decorrelation
- 1.6 The heatmap of the decorrelated data
- 1.7 The correlation matrix after decorrelation
- 1.8 U-MAP Visualization of features
- 1.9 Univariate Analysis
- 1.10 Comparing ILAA vs PCA vs EFA
- 1.11 Effect on CAR modeling
1 Effect of UPSTM-Based Decorrelation on Feature Discovery
1.0.1 Loading the libraries
library("FRESA.CAD")
library(readxl)
library(igraph)
library(umap)
library(tsne)
library(entropy)
library(mlbench)
library(psych)
library(whitening)
library("vioplot")
library("rpart")
op <- par(no.readonly = TRUE)
pander::panderOptions('digits', 3)
pander::panderOptions('table.split.table', 400)
pander::panderOptions('keep.trailing.zeros',TRUE)1.1 Material and Methods
mlBench library
Newman, D.J. & Hettich, S. & Blake, C.L. & Merz, C.J. (1998). UCI Repository of machine learning databases [http://www.ics.uci.edu/~mlearn/MLRepository.html]. Irvine, CA: University of California, Department of Information and Computer Science.
1.2 The Data
#data(PimaIndiansDiabetes)
#pander::pander(table(PimaIndiansDiabetes$diabetes))
#PimaIndiansDiabetes$diabetes <- 1*(PimaIndiansDiabetes$diabetes=="pos")
data("PimaIndiansDiabetes2", package = "mlbench")
PimaIndiansDiabetes <- PimaIndiansDiabetes2[complete.cases(PimaIndiansDiabetes2),]
#data(PimaIndiansDiabetes)
#PimaIndiansDiabetes <- PimaIndiansDiabetes[complete.cases(PimaIndiansDiabetes),]
PimaIndiansDiabetes_mat <- as.data.frame(model.matrix(diabetes~.*.*.,PimaIndiansDiabetes)[,-1])
fnames <- colnames(PimaIndiansDiabetes_mat)
fnames <- str_replace_all(fnames," ","_")
fnames <- str_replace_all(fnames,"/","_")
fnames <- str_replace_all(fnames,":","_x_")
colnames(PimaIndiansDiabetes_mat) <- fnames
pander::pander(table(PimaIndiansDiabetes$diabetes))| neg | pos |
|---|---|
| 262 | 130 |
PimaIndiansDiabetes_mat$diabetes <- 1*(PimaIndiansDiabetes$diabetes=="pos")
1.2.0.1 Standarize the names for the reporting
studyName <- "Diabetes"
dataframe <- PimaIndiansDiabetes_mat
outcome <- "diabetes"
thro <- 0.8
TopVariables <- 3
cexheat = 0.451.3 Generaring the report
1.3.1 Libraries
Some libraries
library(psych)
library(whitening)
library("vioplot")
library("rpart")1.3.2 Data specs
pander::pander(c(rows=nrow(dataframe),col=ncol(dataframe)-1))| rows | col |
|---|---|
| 392 | 92 |
pander::pander(table(dataframe[,outcome]))| 0 | 1 |
|---|---|
| 262 | 130 |
varlist <- colnames(dataframe)
varlist <- varlist[varlist != outcome]
largeSet <- length(varlist) > 1500 1.3.3 Scaling the data
Scaling and removing near zero variance columns and highly co-linear(r>0.99999) columns
### Some global cleaning
sdiszero <- apply(dataframe,2,sd) > 1.0e-16
dataframe <- dataframe[,sdiszero]
varlist <- colnames(dataframe)[colnames(dataframe) != outcome]
tokeep <- c(as.character(correlated_Remove(dataframe,varlist,thr=0.99999)),outcome)
dataframe <- dataframe[,tokeep]
varlist <- colnames(dataframe)
varlist <- varlist[varlist != outcome]
iscontinous <- sapply(apply(dataframe,2,unique),length) >= 5 ## Only variables with enough samples
dataframeScaled <- FRESAScale(dataframe,method="OrderLogit")$scaledData1.4 The heatmap of the data
numsub <- nrow(dataframe)
if (numsub > 1000) numsub <- 1000
if (!largeSet)
{
hm <- heatMaps(data=dataframeScaled[1:numsub,],
Outcome=outcome,
Scale=TRUE,
hCluster = "row",
xlab="Feature",
ylab="Sample",
srtCol=45,
srtRow=45,
cexCol=cexheat,
cexRow=cexheat
)
par(op)
}
1.4.0.1 Correlation Matrix of the Data
The heat map of the data
if (!largeSet)
{
par(cex=0.6,cex.main=0.85,cex.axis=0.7)
#cormat <- Rfast::cora(as.matrix(dataframe[,varlist]),large=TRUE)
cormat <- cor(dataframe[,varlist],method="pearson")
cormat[is.na(cormat)] <- 0
gplots::heatmap.2(abs(cormat),
trace = "none",
# scale = "row",
mar = c(5,5),
col=rev(heat.colors(5)),
main = "Original Correlation",
cexRow = cexheat,
cexCol = cexheat,
srtCol=45,
srtRow=45,
key.title=NA,
key.xlab="|Pearson Correlation|",
xlab="Feature", ylab="Feature")
diag(cormat) <- 0
print(max(abs(cormat)))
}
[1]
0.9860671
1.5 The decorrelation
DEdataframe <- IDeA(dataframe,verbose=TRUE,thr=thro)
#>
#> pregnant_x_pressure_x_age pregnant_x_pressure_x_insulin pregnant_x_pressure_x_pedigree insulin_x_mass_x_pedigree glucose_x_triceps_x_insulin pressure_x_insulin_x_age
#> pregnant glucose pressure triceps insulin mass
#> 0.83695652 0.03260870 0.01086957 0.13043478 0.54347826 0.04347826
#>
#> Included: 92 , Uni p: 0.001630435 , Base Size: 11 , Rcrit: 0.1482456
#>
#>
1 <R=0.986,thr=0.950>, Top: 15< 3 >[Fa= 15 ]( 15 , 39 , 0 ),<|><>Tot Used: 54 , Added: 39 , Zero Std: 0 , Max Cor: 0.965
#>
2 <R=0.965,thr=0.950>, Top: 2< 2 >[Fa= 17 ]( 2 , 4 , 15 ),<|><>Tot Used: 57 , Added: 4 , Zero Std: 0 , Max Cor: 0.950
#>
3 <R=0.950,thr=0.950>, Top: 1< 1 >[Fa= 18 ]( 1 , 1 , 17 ),<|><>Tot Used: 57 , Added: 1 , Zero Std: 0 , Max Cor: 0.949
#>
4 <R=0.949,thr=0.900>, Top: 22< 2 >[Fa= 29 ]( 22 , 32 , 18 ),<|><>Tot Used: 83 , Added: 32 , Zero Std: 0 , Max Cor: 0.949
#>
5 <R=0.949,thr=0.900>, Top: 5< 1 >[Fa= 34 ]( 5 , 5 , 29 ),<|><>Tot Used: 84 , Added: 5 , Zero Std: 0 , Max Cor: 0.900
#>
6 <R=0.900,thr=0.800>, Top: 20< 1 >[Fa= 40 ]( 16 , 24 , 34 ),<|><>Tot Used: 87 , Added: 24 , Zero Std: 0 , Max Cor: 0.858
#>
7 <R=0.858,thr=0.800>, Top: 2< 1 >[Fa= 41 ]( 2 , 2 , 40 ),<|><>Tot Used: 89 , Added: 2 , Zero Std: 0 , Max Cor: 0.851
#>
8 <R=0.851,thr=0.800>, Top: 2< 1 >[Fa= 41 ]( 1 , 1 , 41 ),<|><>Tot Used: 89 , Added: 1 , Zero Std: 0 , Max Cor: 0.797
#>
9 <R=0.797,thr=0.800>
#>
[ 9 ], 0.7969239 Decor Dimension: 89 Nused: 89 . Cor to Base: 62 , ABase: 92 , Outcome Base: 0
#>
varlistc <- colnames(DEdataframe)[colnames(DEdataframe) != outcome]
pander::pander(sum(apply(dataframe[,varlist],2,var)))4.99e+12
pander::pander(sum(apply(DEdataframe[,varlistc],2,var)))1.05e+12
pander::pander(entropy(discretize(unlist(dataframe[,varlist]), 256)))1.13
pander::pander(entropy(discretize(unlist(DEdataframe[,varlistc]), 256)))0.918
1.5.1 The decorrelation matrix
if (!largeSet)
{
par(cex=0.6,cex.main=0.85,cex.axis=0.7)
UPLTM <- attr(DEdataframe,"UPLTM")
gplots::heatmap.2(1.0*(abs(UPLTM)>0),
trace = "none",
mar = c(5,5),
col=rev(heat.colors(5)),
main = "Decorrelation matrix",
cexRow = cexheat,
cexCol = cexheat,
srtCol=45,
srtRow=45,
key.title=NA,
key.xlab="|Beta|>0",
xlab="Output Feature", ylab="Input Feature")
par(op)
}
1.5.2 Formulas Network
Displaying the features associations
par(op)
if ((ncol(dataframe) < 1000) && (ncol(dataframe)>10))
{
DEdataframeB <- ILAA(dataframe,verbose=TRUE,thr=thro,bootstrap=30)
transform <- 1*(attr(DEdataframeB,"UPLTM") != 0)
print(ncol(transform))
thrcol <- 1 + 0.025*nrow(transform)
rsum <- apply(1*(transform !=0),1,sum) > 2
csum <- apply(1*(transform !=0),2,sum) > thrcol | rsum
transform <- transform[csum,csum]
csum <- (apply(1*(transform !=0),2,sum) > 1) & (apply(1*(transform !=0),1,sum) > 1)
transform <- transform[csum,csum]
print(ncol(transform))
if (ncol(transform)>100)
{
thrcol <- 1 + 0.10*nrow(transform)
rsum <- apply(1*(transform !=0),1,sum) > 4
csum <- apply(1*(transform !=0),2,sum) > thrcol | rsum
transform <- transform[csum,csum]
csum <- (apply(1*(transform !=0),2,sum) > 3) & (apply(1*(transform !=0),1,sum) > 3)
transform <- transform[csum,csum]
}
print(ncol(transform))
if (ncol(transform)>100)
{
thrcol <- 1 + 0.20*nrow(transform)
rsum <- apply(1*(transform !=0),1,sum) > 8
csum <- apply(1*(transform !=0),2,sum) > thrcol | rsum
transform <- transform[csum,csum]
csum <- (apply(1*(transform !=0),2,sum) > 7) & (apply(1*(transform !=0),1,sum) > 7)
transform <- transform[csum,csum]
}
print(ncol(transform))
if ((ncol(transform) > 10) && (ncol(transform) < 150))
{
gplots::heatmap.2(transform,
trace = "none",
mar = c(5,5),
col=rev(heat.colors(5)),
main = "Red Decorrelation matrix",
cexRow = cexheat,
cexCol = cexheat,
srtCol=45,
srtRow=45,
key.title=NA,
key.xlab="|Beta|>0",
xlab="Output Feature", ylab="Input Feature")
par(op)
colnames(transform) <- str_remove_all(colnames(transform),"La_")
VertexSize <- apply(transform,2,mean)
VertexSize <- 5*VertexSize/max(VertexSize)
gr <- graph_from_adjacency_matrix(transform,mode = "directed",diag = FALSE,weighted=TRUE)
gr$layout <- layout_with_fr
fc <- cluster_optimal(gr)
plot(fc, gr,
edge.width = 0.5*E(gr)$weight,
vertex.size=VertexSize,
edge.arrow.size=0.5,
edge.arrow.width=0.5,
vertex.label.cex=0.65,
vertex.label.dist=1,
main="Feature Association")
}
}
#> fast | LM |
#> pregnant_x_pressure_x_age pregnant_x_pressure_x_insulin pregnant_x_pressure_x_pedigree insulin_x_mass_x_pedigree glucose_x_triceps_x_insulin pressure_x_insulin_x_age
#> pregnant glucose pressure triceps insulin mass
#> 0.83695652 0.03260870 0.01086957 0.13043478 0.54347826 0.04347826
#>
#> Included: 92 , Uni p: 0.001630435 , Base Size: 11 , Rcrit: 0.1482456
#>
#>
1 <R=0.986,thr=0.950>, Top: 15< 3 >[Fa= 15 ]( 15 , 39 , 0 ),<|><>Tot Used: 54 , Added: 39 , Zero Std: 0 , Max Cor: 0.965
#>
2 <R=0.965,thr=0.950>, Top: 2< 2 >[Fa= 17 ]( 2 , 4 , 15 ),<|><>Tot Used: 57 , Added: 4 , Zero Std: 0 , Max Cor: 0.950
#>
3 <R=0.950,thr=0.950>, Top: 1< 1 >[Fa= 18 ]( 1 , 1 , 17 ),<|><>Tot Used: 57 , Added: 1 , Zero Std: 0 , Max Cor: 0.949
#>
4 <R=0.949,thr=0.900>, Top: 22< 2 >[Fa= 29 ]( 22 , 32 , 18 ),<|><>Tot Used: 83 , Added: 32 , Zero Std: 0 , Max Cor: 0.949
#>
5 <R=0.949,thr=0.900>, Top: 5< 1 >[Fa= 34 ]( 5 , 5 , 29 ),<|><>Tot Used: 84 , Added: 5 , Zero Std: 0 , Max Cor: 0.900
#>
6 <R=0.900,thr=0.800>, Top: 20< 1 >[Fa= 40 ]( 16 , 24 , 34 ),<|><>Tot Used: 87 , Added: 24 , Zero Std: 0 , Max Cor: 0.858
#>
7 <R=0.858,thr=0.800>, Top: 2< 1 >[Fa= 41 ]( 2 , 2 , 40 ),<|><>Tot Used: 89 , Added: 2 , Zero Std: 0 , Max Cor: 0.851
#>
8 <R=0.851,thr=0.800>, Top: 2< 1 >[Fa= 41 ]( 1 , 1 , 41 ),<|><>Tot Used: 89 , Added: 1 , Zero Std: 0 , Max Cor: 0.797
#>
9 <R=0.797,thr=0.800>
#>
[ 9 ], 0.7969239 Decor Dimension: 89 Nused: 89 . Cor to Base: 62 , ABase: 92 , Outcome Base: 0
#>
bootstrapping->..............................
#>
[1] 89
#> [1] 71
#> [1] 71
#> [1] 71
par(op)1.6 The heatmap of the decorrelated data
if (!largeSet)
{
hm <- heatMaps(data=DEdataframe[1:numsub,],
Outcome=outcome,
Scale=TRUE,
hCluster = "row",
cexRow = cexheat,
cexCol = cexheat,
srtCol=45,
srtRow=45,
xlab="Feature",
ylab="Sample")
par(op)
}
1.7 The correlation matrix after decorrelation
if (!largeSet)
{
cormat <- cor(DEdataframe[,varlistc],method="pearson")
cormat[is.na(cormat)] <- 0
gplots::heatmap.2(abs(cormat),
trace = "none",
mar = c(5,5),
col=rev(heat.colors(5)),
main = "Correlation after ILAA",
cexRow = cexheat,
cexCol = cexheat,
srtCol=45,
srtRow=45,
key.title=NA,
key.xlab="|Pearson Correlation|",
xlab="Feature", ylab="Feature")
par(op)
diag(cormat) <- 0
print(max(abs(cormat)))
}
[1]
0.7969239
1.8 U-MAP Visualization of features
1.8.1 The UMAP based on LASSO on Raw Data
if (nrow(dataframe) < 1000)
{
classes <- unique(dataframe[1:numsub,outcome])
raincolors <- rainbow(length(classes))
names(raincolors) <- classes
datasetframe.umap = umap(scale(dataframe[1:numsub,varlist]),n_components=2)
plot(datasetframe.umap$layout,xlab="U1",ylab="U2",main="UMAP: Original",t='n')
text(datasetframe.umap$layout,labels=dataframe[1:numsub,outcome],col=raincolors[dataframe[1:numsub,outcome]+1])
}
1.8.2 The decorralted UMAP
if (nrow(dataframe) < 1000)
{
datasetframe.umap = umap(scale(DEdataframe[1:numsub,varlistc]),n_components=2)
plot(datasetframe.umap$layout,xlab="U1",ylab="U2",main="UMAP: After ILAA",t='n')
text(datasetframe.umap$layout,labels=DEdataframe[1:numsub,outcome],col=raincolors[DEdataframe[1:numsub,outcome]+1])
}
1.9 Univariate Analysis
1.9.1 Univariate
univarRAW <- uniRankVar(varlist,
paste(outcome,"~1"),
outcome,
dataframe,
rankingTest="AUC")
univarDe <- uniRankVar(varlistc,
paste(outcome,"~1"),
outcome,
DEdataframe,
rankingTest="AUC",
)
1.9.2 Final Table
univariate_columns <- c("caseMean","caseStd","controlMean","controlStd","controlKSP","ROCAUC")
##top variables
topvar <- c(1:length(varlist)) <= TopVariables
tableRaw <- univarRAW$orderframe[topvar,univariate_columns]
pander::pander(tableRaw)| caseMean | caseStd | controlMean | controlStd | controlKSP | ROCAUC | |
|---|---|---|---|---|---|---|
| glucose_x_mass_x_age | 186646 | 75784 | 102786 | 53357 | 8.45e-05 | 0.845 |
| glucose_x_age | 5278 | 2104 | 3206 | 1444 | 9.98e-07 | 0.825 |
| glucose_x_mass | 5189 | 1429 | 3563 | 1209 | 1.02e-01 | 0.821 |
topLAvar <- univarDe$orderframe$Name[str_detect(univarDe$orderframe$Name,"La_")]
topLAvar <- unique(c(univarDe$orderframe$Name[topvar],topLAvar[1:as.integer(TopVariables/2)]))
finalTable <- univarDe$orderframe[topLAvar,univariate_columns]
pander::pander(finalTable)| caseMean | caseStd | controlMean | controlStd | controlKSP | ROCAUC | |
|---|---|---|---|---|---|---|
| glucose_x_pressure_x_age | 397284 | 184042.7 | 225271 | 119951.9 | 2.10e-04 | 0.809 |
| glucose | 145 | 29.8 | 111 | 24.6 | 3.43e-02 | 0.806 |
| glucose_x_triceps_x_insulin | 1054818 | 904289.8 | 465722 | 612619.7 | 6.61e-13 | 0.787 |
| La_insulin_x_mass_x_age | 31742 | 29242.4 | 15567 | 22041.9 | 3.18e-09 | 0.713 |
dc <- getLatentCoefficients(DEdataframe)
fscores <- attr(DEdataframe,"fscore")
pander::pander(c(mean=mean(sapply(dc,length)),total=length(dc),fraction=length(dc)/(ncol(dataframe)-1)))| mean | total | fraction |
|---|---|---|
| 2.82 | 76 | 0.826 |
theCharformulas <- attr(dc,"LatentCharFormulas")
finalTable <- rbind(finalTable,tableRaw[topvar[!(topvar %in% topLAvar)],univariate_columns])
orgnamez <- rownames(finalTable)
orgnamez <- str_remove_all(orgnamez,"La_")
finalTable$RAWAUC <- univarRAW$orderframe[orgnamez,"ROCAUC"]
finalTable$DecorFormula <- theCharformulas[rownames(finalTable)]
finalTable$fscores <- fscores[rownames(finalTable)]
Final_Columns <- c("DecorFormula","caseMean","caseStd","controlMean","controlStd","controlKSP","ROCAUC","RAWAUC","fscores")
finalTable <- finalTable[order(-finalTable$ROCAUC),]
pander::pander(finalTable[,Final_Columns])| DecorFormula | caseMean | caseStd | controlMean | controlStd | controlKSP | ROCAUC | RAWAUC | fscores | |
|---|---|---|---|---|---|---|---|---|---|
| glucose_x_mass_x_age | NA | 186646 | 75783.6 | 102786 | 53357.3 | 8.45e-05 | 0.845 | 0.845 | NA |
| glucose_x_age | NA | 5278 | 2103.8 | 3206 | 1444.5 | 9.98e-07 | 0.825 | 0.825 | NA |
| glucose_x_mass | NA | 5189 | 1429.4 | 3563 | 1208.6 | 1.02e-01 | 0.821 | 0.821 | NA |
| glucose_x_pressure_x_age | NA | 397284 | 184042.7 | 225271 | 119951.9 | 2.10e-04 | 0.809 | 0.809 | 4 |
| glucose | NA | 145 | 29.8 | 111 | 24.6 | 3.43e-02 | 0.806 | 0.806 | NA |
| glucose_x_triceps_x_insulin | NA | 1054818 | 904289.8 | 465722 | 612619.7 | 6.61e-13 | 0.787 | 0.787 | 5 |
| La_insulin_x_mass_x_age | + (0.106)glucose_x_pressure_x_insulin - (0.201)glucose_x_insulin_x_mass - (0.452)pressure_x_insulin_x_age + insulin_x_mass_x_age | 31742 | 29242.4 | 15567 | 22041.9 | 3.18e-09 | 0.713 | 0.791 | -2 |
1.10 Comparing ILAA vs PCA vs EFA
1.10.1 PCA
featuresnames <- colnames(dataframe)[colnames(dataframe) != outcome]
pc <- prcomp(dataframe[,iscontinous],center = TRUE,scale. = TRUE) #principal components
predPCA <- predict(pc,dataframe[,iscontinous])
PCAdataframe <- as.data.frame(cbind(predPCA,dataframe[,!iscontinous]))
colnames(PCAdataframe) <- c(colnames(predPCA),colnames(dataframe)[!iscontinous])
#plot(PCAdataframe[,colnames(PCAdataframe)!=outcome],col=dataframe[,outcome],cex=0.65,cex.lab=0.5,cex.axis=0.75,cex.sub=0.5,cex.main=0.75)
#pander::pander(pc$rotation)
PCACor <- cor(PCAdataframe[,colnames(PCAdataframe) != outcome])
gplots::heatmap.2(abs(PCACor),
trace = "none",
# scale = "row",
mar = c(5,5),
col=rev(heat.colors(5)),
main = "PCA Correlation",
cexRow = 0.5,
cexCol = 0.5,
srtCol=45,
srtRow= -45,
key.title=NA,
key.xlab="Pearson Correlation",
xlab="Feature", ylab="Feature")
1.10.2 EFA
EFAdataframe <- dataframeScaled
if (length(iscontinous) < 2000)
{
topred <- min(length(iscontinous),nrow(dataframeScaled),ncol(predPCA)/2)
if (topred < 2) topred <- 2
uls <- fa(dataframeScaled[,iscontinous],nfactors=topred,rotate="varimax",warnings=FALSE) # EFA analysis
predEFA <- predict(uls,dataframeScaled[,iscontinous])
EFAdataframe <- as.data.frame(cbind(predEFA,dataframeScaled[,!iscontinous]))
colnames(EFAdataframe) <- c(colnames(predEFA),colnames(dataframeScaled)[!iscontinous])
EFACor <- cor(EFAdataframe[,colnames(EFAdataframe) != outcome])
gplots::heatmap.2(abs(EFACor),
trace = "none",
# scale = "row",
mar = c(5,5),
col=rev(heat.colors(5)),
main = "EFA Correlation",
cexRow = 0.5,
cexCol = 0.5,
srtCol=45,
srtRow= -45,
key.title=NA,
key.xlab="Pearson Correlation",
xlab="Feature", ylab="Feature")
}
1.11 Effect on CAR modeling
par(op)
par(xpd = TRUE)
dataframe[,outcome] <- factor(dataframe[,outcome])
rawmodel <- rpart(paste(outcome,"~."),dataframe,control=rpart.control(maxdepth=3))
pr <- predict(rawmodel,dataframe,type = "class")
ptab <- list(er="Error",detail=matrix(nrow=6,ncol=1))
if (length(unique(pr))>1)
{
plot(rawmodel,main="Raw",branch=0.5,uniform = TRUE,compress = TRUE,margin=0.1)
text(rawmodel, use.n = TRUE,cex=0.75)
ptab <- epiR::epi.tests(table(pr==0,dataframe[,outcome]==0))
}
pander::pander(table(dataframe[,outcome],pr))| 0 | 1 | |
|---|---|---|
| 0 | 230 | 32 |
| 1 | 29 | 101 |
pander::pander(ptab$detail[c(5,3,4,6),])| statistic | est | lower | upper | |
|---|---|---|---|---|
| 5 | diag.ac | 0.844 | 0.805 | 0.879 |
| 3 | se | 0.777 | 0.696 | 0.845 |
| 4 | sp | 0.878 | 0.832 | 0.915 |
| 6 | diag.or | 25.032 | 14.380 | 43.574 |
par(op)
par(xpd = TRUE)
DEdataframe[,outcome] <- factor(DEdataframe[,outcome])
IDeAmodel <- rpart(paste(outcome,"~."),DEdataframe,control=rpart.control(maxdepth=3))
pr <- predict(IDeAmodel,DEdataframe,type = "class")
ptab <- list(er="Error",detail=matrix(nrow=6,ncol=1))
if (length(unique(pr))>1)
{
plot(IDeAmodel,main="ILAA",branch=0.5,uniform = TRUE,compress = TRUE,margin=0.1)
text(IDeAmodel, use.n = TRUE,cex=0.75)
ptab <- epiR::epi.tests(table(pr==0,DEdataframe[,outcome]==0))
}
pander::pander(table(DEdataframe[,outcome],pr))| 0 | 1 | |
|---|---|---|
| 0 | 223 | 39 |
| 1 | 32 | 98 |
pander::pander(ptab$detail[c(5,3,4,6),])| statistic | est | lower | upper | |
|---|---|---|---|---|
| 5 | diag.ac | 0.819 | 0.777 | 0.856 |
| 3 | se | 0.754 | 0.671 | 0.825 |
| 4 | sp | 0.851 | 0.802 | 0.892 |
| 6 | diag.or | 17.511 | 10.365 | 29.584 |
par(op)
par(xpd = TRUE)
PCAdataframe[,outcome] <- factor(PCAdataframe[,outcome])
PCAmodel <- rpart(paste(outcome,"~."),PCAdataframe,control=rpart.control(maxdepth=3))
pr <- predict(PCAmodel,PCAdataframe,type = "class")
ptab <- list(er="Error",detail=matrix(nrow=6,ncol=1))
if (length(unique(pr))>1)
{
plot(PCAmodel,main="PCA",branch=0.5,uniform = TRUE,compress = TRUE,margin=0.1)
text(PCAmodel, use.n = TRUE,cex=0.75)
ptab <- epiR::epi.tests(table(pr==0,PCAdataframe[,outcome]==0))
}
pander::pander(table(PCAdataframe[,outcome],pr))| 0 | 1 | |
|---|---|---|
| 0 | 236 | 26 |
| 1 | 43 | 87 |
pander::pander(ptab$detail[c(5,3,4,6),])| statistic | est | lower | upper | |
|---|---|---|---|---|
| 5 | diag.ac | 0.824 | 0.783 | 0.860 |
| 3 | se | 0.669 | 0.581 | 0.749 |
| 4 | sp | 0.901 | 0.858 | 0.934 |
| 6 | diag.or | 18.365 | 10.644 | 31.687 |
par(op)1.11.1 EFA
EFAdataframe[,outcome] <- factor(EFAdataframe[,outcome])
EFAmodel <- rpart(paste(outcome,"~."),EFAdataframe,control=rpart.control(maxdepth=3))
pr <- predict(EFAmodel,EFAdataframe,type = "class")
ptab <- list(er="Error",detail=matrix(nrow=6,ncol=1))
if (length(unique(pr))>1)
{
plot(EFAmodel,main="EFA",branch=0.5,uniform = TRUE,compress = TRUE,margin=0.1)
text(EFAmodel, use.n = TRUE,cex=0.75)
ptab <- epiR::epi.tests(table(pr==0,EFAdataframe[,outcome]==0))
}
pander::pander(table(EFAdataframe[,outcome],pr))| 0 | 1 | |
|---|---|---|
| 0 | 223 | 39 |
| 1 | 39 | 91 |
pander::pander(ptab$detail[c(5,3,4,6),])| statistic | est | lower | upper | |
|---|---|---|---|---|
| 5 | diag.ac | 0.801 | 0.758 | 0.839 |
| 3 | se | 0.700 | 0.613 | 0.777 |
| 4 | sp | 0.851 | 0.802 | 0.892 |
| 6 | diag.or | 13.342 | 8.041 | 22.138 |
par(op)